An early design estimation approach to synthesize the low-power pre-computation-based content addressable memory

摘要

Content addressable memory (CAM) is often used in many applications which require searching in high speed such as network router, translation look-aside buffer (TLB), Huffman decoding, discrete cosine transform or the applications having quick lookup table operation. Due to its operational characteristic of parallel data searching, the power consumption is also exacerbated. In this paper, we propose a methodology for synthesizing a low power pre-computation-based content addressable memory (PB-CAM) effectively. The concept of discrete uniform distribution is adopted in pre-computation block so as to verify the outcomes of power reduction when the adaptive parameter extractors are synthesized in a different manner. With our proposed approach, we are able to estimate the tendency towards power consumption efficiently and determine which type of parameter extractor is superior in power reduction for the specific data. Experiment shows the power consumption of our approach is better by at least 29% compared with original parameter extractors.